Prediction of a metric of quality of a network

Abstract

An apparatus ( 100 ) for building a prediction model comprises means for collecting a plurality of high-paced telemetry traffic measurement values ( 4 ) representing traffic rates observed in a shared medium of the point-to-multipoint telecommunications network ( 1 ), means for fitting at least one traffic model ( 5 ) using the plurality of high-paced telemetry traffic measurement values ( 4 ) and computing at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network using the traffic model ( 5 ), wherein the metric of the quality relates to at least one individual user, and means for training a prediction model ( 7 ) on a simulated dataset ( 6 ), wherein the simulated dataset ( 6 ) comprises the descriptor of at least one network configuration and the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network, the prediction model ( 7 ) being configured to compute the value of the metric of the quality of the point-to-multipoint telecommunications network.

1 . An apparatus ( 100 ) for building a prediction model adapted to predict a value of a metric of a quality of a point-to-multipoint telecommunications network, the apparatus comprising means for:
 Collecting a plurality of high-paced telemetry traffic measurement values ( 4 ) representing traffic rates observed in a shared medium of the point-to-multipoint telecommunications network ( 1 ), wherein the shared medium is shared by a plurality of users of the point-to-multipoint telecommunications network and wherein the high-paced telemetry traffic measurement values represent traffic rates attributed to individual users among the plurality of users,   Fitting at least one traffic model ( 5 ) using the plurality of high-paced telemetry traffic measurement values ( 4 ) and computing at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network using the traffic model ( 5 ) and a descriptor ( 334 ) of at least one network configuration, wherein the metric of the quality of the point-to-multipoint telecommunications network relates to at least one individual user of the point-to-multipoint telecommunications network,   Training a prediction model ( 7 ) on a simulated dataset ( 6 ), wherein the simulated dataset ( 6 ) comprises the descriptor of at least one network configuration and the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network, the prediction model ( 7 ) being configured to compute the value of the metric of the quality of the point-to-multipoint telecommunications network.   
     
     
         2 . An apparatus according to  claim 1 , wherein the plurality of high-paced telemetry traffic measurement values ( 4 ) is retrieved from a minority of users of the point-to-multipoint telecommunications network. 
     
     
         3 . An apparatus according to  claim 1  wherein the descriptor ( 334 ) of at least one network configuration comprises at least one value relating to a dynamic bandwidth management system. 
     
     
         4 . An apparatus according to  claim 1 , wherein the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network comprises a plurality of simulated values of the metric of the quality of the point-to-multipoint telecommunications network, wherein the metric of the quality of the point-to-multipoint telecommunications network is selected in the group consisting of data rates, latencies and speedtest results. 
     
     
         5 . An apparatus according to  claim 1 , wherein the apparatus further comprises means for:
 Extracting a plurality of elementary segments ( 401 ) from the plurality of high-paced telemetry traffic measurement values,   Clustering the plurality of elementary segments ( 401 ) into a plurality of clusters of elementary segments ( 322 ),   Fitting a plurality of cluster traffic models ( 324 ) on the plurality of clusters of elementary segments ( 322 ),   wherein the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network is computed using at least one of the plurality of cluster traffic models and the descriptor of at least one network configuration.   
     
     
         6 . An apparatus according to  claim 1 , wherein the at least one traffic model ( 5 ) comprises a Discrete Auto Regressive model. 
     
     
         7 . An apparatus according to  claim 1 , wherein the at least one network configuration comprises a plurality of network configurations and the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network comprises a plurality of simulated values of the metric of the quality of the point-to-multipoint telecommunications network. 
     
     
         8 . An apparatus according to  claim 1 , wherein the prediction model ( 7 ) comprises a classifier. 
     
     
         9 . An apparatus according to  claim 1 , wherein the prediction model ( 7 ) comprises a regression model. 
     
     
         10 . An apparatus according to  claim 1 , wherein the point-to-multipoint telecommunications network ( 1 ) is a Passive Optical Network. 
     
     
         11 . An apparatus according to  claim 1 , wherein the prediction model ( 7 ) computes a probability of success of a speedtest. 
     
     
         12 . An apparatus according to  claim 1 , wherein the prediction model ( 7 ) computes a speedtest rate. 
     
     
         13 . A method for building a prediction model adapted to predict a value of a metric of a quality of a point-to-multipoint telecommunications network, the method comprising the steps of:
 Collecting a plurality of high-paced telemetry traffic measurement values ( 4 ) representing traffic rates observed in a shared medium of the point-to-multipoint telecommunications network ( 1 ), wherein the shared medium is shared by a plurality of users of the point-to-multipoint telecommunications network and wherein the high-paced telemetry traffic measurement values represent traffic rates attributed to individual users among the plurality of users,   Fitting at least one traffic model ( 5 ) using the plurality of high-paced telemetry traffic measurement values ( 4 ) and computing at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network using the traffic model ( 5 ) and a descriptor ( 334 ) of at least one network configuration, wherein the metric of the quality of the point-to-multipoint telecommunications network relates to at least one individual user of the point-to-multipoint telecommunications network,   Training a prediction model ( 7 ) on a simulated dataset ( 6 ), wherein the simulated dataset ( 6 ) comprises the descriptor of at least one network configuration and the at least one simulated value of the metric of the quality of the point-to-multipoint telecommunications network, the prediction model ( 7 ) being configured to compute the value of the metric of the quality of the point-to-multipoint telecommunications network.   
     
     
         14 . An apparatus ( 31 ) for predicting a value of a metric of a quality of a point-to-multipoint telecommunications network, the apparatus comprising means for:
 Collecting a real-time telemetry traffic measurement value ( 8 ),   Using the prediction model ( 7 ) built according to the method according to  claim 13  to predict a value of the metric of the quality ( 9 ) of the point-to-multipoint telecommunications network ( 1 ).   
     
     
         15 . A method for predicting a value of a metric of a quality of a point-to-multipoint telecommunications network, the method comprising the steps of:
 Collecting a real-time telemetry traffic measurement value ( 8 ),   Using the prediction model ( 7 ) built according to the method according to  claim 13  to predict a value of the metric of the quality ( 9 ) of the point-to-multipoint telecommunications network ( 1 ).